Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 17 insertions, 11 deletions

diff --git a/net/socket.c b/net/socket.c
index 792f0313ea91..e6945e318f02 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -252,7 +252,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
         init_waitqueue_head(&wq->wait);
         wq->fasync_list = NULL;
         wq->flags = 0;
-        RCU_INIT_POINTER(ei->socket.wq, wq);
+        ei->socket.wq = wq;
 
         ei->socket.state = SS_UNCONNECTED;
         ei->socket.flags = 0;
@@ -266,11 +266,9 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 static void sock_destroy_inode(struct inode *inode)
 {
         struct socket_alloc *ei;
-        struct socket_wq *wq;
 
         ei = container_of(inode, struct socket_alloc, vfs_inode);
-        wq = rcu_dereference_protected(ei->socket.wq, 1);
-        kfree_rcu(wq, rcu);
+        kfree_rcu(ei->socket.wq, rcu);
         kmem_cache_free(sock_inode_cachep, ei);
 }
 
@@ -585,7 +583,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
                 module_put(owner);
         }
 
-        if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
+        if (sock->wq->fasync_list)
                 pr_err("%s: fasync list not empty!\n", __func__);
 
         if (!sock->file) {
@@ -1112,12 +1110,21 @@ EXPORT_SYMBOL(sock_create_lite);
 static __poll_t sock_poll(struct file *file, poll_table *wait)
 {
         struct socket *sock = file->private_data;
-        __poll_t events = poll_requested_events(wait);
+        __poll_t events = poll_requested_events(wait), flag = 0;
 
-        sock_poll_busy_loop(sock, events);
         if (!sock->ops->poll)
                 return 0;
-        return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
+
+        if (sk_can_busy_loop(sock->sk)) {
+                /* poll once if requested by the syscall */
+                if (events & POLL_BUSY_LOOP)
+                        sk_busy_loop(sock->sk, 1);
+
+                /* if this socket can poll_ll, tell the system call */
+                flag = POLL_BUSY_LOOP;
+        }
+
+        return sock->ops->poll(file, sock, wait) | flag;
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1154,7 +1161,7 @@ static int sock_fasync(int fd, struct file *filp, int on)
                 return -EINVAL;
 
         lock_sock(sk);
-        wq = rcu_dereference_protected(sock->wq, lockdep_sock_is_held(sk));
+        wq = sock->wq;
         fasync_helper(fd, filp, on, &wq->fasync_list);
 
         if (!wq->fasync_list)
@@ -2671,8 +2678,7 @@ EXPORT_SYMBOL(sock_unregister);
 
 bool sock_is_registered(int family)
 {
-        return family < NPROTO &&
-                rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]);
+        return family < NPROTO && rcu_access_pointer(net_families[family]);
 }
 
 static int __init sock_init(void)